Gemini 2.5 Pro Preview • Hacker News Board

Re: Gemini 2.5 Pro Preview

#41

Post by white_beach » Tue, May 06, 2025, 3:43 PM UTC

object?

(aider joke)

Re: Gemini 2.5 Pro Preview

#42

Post by llm_nerd » Tue, May 06, 2025, 3:43 PM UTC

Their nomenclature is a bit confused. The Gemini web app has a 2.5 Pro (experimental), yet this apparently is referring to 2.5 Pro Preview 05-06.

Would be ideal if they incremented the version number or the like.

Re: Gemini 2.5 Pro Preview

#43

Post by martinald » Tue, May 06, 2025, 3:43 PM UTC

I'm totally lost again! If I use Gemini on the website (gemini.google.com), am I using 2.5 Pro IO edition, or am I using the old one?

Re: Gemini 2.5 Pro Preview

#44

Post by uh_uh » Tue, May 06, 2025, 3:44 PM UTC

herpdyderp wrote: post #22

I agree it's very good but the UI is still usually an unusable, scroll-jacking disaster. I've found it's best to let a chat sit for around a few minutes after it has finished printing the AI's output. Finding the `ms-code-block` element in dev tools and logging `$0.textContext` is reliable too.

Noticed this too. There's something funny about billion dollar models being handicapped by stuck buttons.

Re: Gemini 2.5 Pro Preview

#45

Post by hiddencost » Tue, May 06, 2025, 3:46 PM UTC

djrj477dhsnv wrote: post #36

I don't understand what I'm doing wrong.. it seems like everyone is saying Gemini is better, but I've compared dozens of examples from my work, and Grok has always produced better results.

[flagged]

Re: Gemini 2.5 Pro Preview

#46

Post by mattlondon » Tue, May 06, 2025, 3:46 PM UTC

ksec wrote: post #40

segphault wrote: post #18

My frustration with using these models for programming in the past has largely been around their tendency to hallucinate APIs that simply don't exist. The Gemini 2.5 models, both pro and flash, seem significantly less susceptible to this than any other model I've tried. There are still significant limitations, no amount of prompting will get current models to approach abstraction and architecture the way a person doe…

I have been asking if AI without hallucination, coding or not is possible but so far with no real concrete answer.

It's already much improved on the early days.

But I wonder when we'll be happy? Do we expect colleagues friends and family to be 100% laser-accurate 100% of the time? I'd wager we don't. Should we expect that from an artificial intelligence too?

Re: Gemini 2.5 Pro Preview

#47

Post by oellegaard » Tue, May 06, 2025, 3:46 PM UTC

Is there anything like Claude code for other models such as gemini?

Re: Gemini 2.5 Pro Preview

#48

Post by crat3r » Tue, May 06, 2025, 3:47 PM UTC

jeffbee wrote: post #35

crat3r wrote: post #27

So, are people using these tools without the org they work for knowing? The amount of hoops I would have to jump through to get either of the smaller companies I have worked for since the AI boom to let me use a tool like this would make it absolutely not worth the effort. I'm assuming large companies are mandating it, but ultimately the work that these LLMs seem poised for would benefit smaller companies most and I…

Not every coding task is something you want to check into your repo. I have mostly used Gemini to generate random crud. For example I had a huge JSON representation of a graph, and I wanted the graph modified in a given way, and I wanted it printed out on my terminal in color. None of which I was remotely interested in writing, so I let a robot do it and it was fine.

Fair, but I am seeing so much talk about how it is completing actual SDE tickets. Maybe not this model specifically, but to be honest I don't care about generating dummy data, I care about the claims that these newer models are on par with junior engineers.

Junior engineers will complete a task to update an API, or fix a bug on the front-end, within a couple days with lets say 80 percent certainty they hit the mark (maybe an inflated metric). How are people comparing the output of these models to that of a junior engineer if they generally just say "Here is some of my code, what's wrong with it?". That certainly isn't taking a real ticket and completing it in any capacity.

I am obviously very skeptical but mostly I want to try one of these models myself but in reality I think that my higher-ups would think that they introduce both risk AND the potential for major slacking off haha.

Re: Gemini 2.5 Pro Preview

#49

Post by ziml77 » Tue, May 06, 2025, 3:47 PM UTC

ChadMoran wrote: post #24

GaggiX wrote: post #15

Earlier quoted context omitted.

You can ask to not use comments or use less comments, you can put this in the system prompt too.

I've tried this, aggressively and it still does it for me. I gave up.

I tried this as well. I'm interfacing with Gemini 2.5 using Cursor and I have rules to to limit the comments. It still ends up over-commenting.

Re: Gemini 2.5 Pro Preview

#50

Post by blensor » Tue, May 06, 2025, 3:47 PM UTC

GaggiX wrote: post #15

ranyume wrote: post #11

I don't know if I'm doing something wrong, but every time I ask gemini 2.5 for code it outputs SO MANY comments. An exaggerated amount of comments. Sections comments, step comments, block comments, inline comments, all the gang.

You can ask to not use comments or use less comments, you can put this in the system prompt too.

Maybe too many comments could be a good metric to check if someone just yolo accepted the result or if they actually checked if it's correct.

I don't have problems with getting lot's of comments in the output, I am just deleting it while reading what it did